{"total":275,"rows":[{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566,"area":null},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395,"area":null},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341,"area":null},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286,"area":null},{"id":"2308.08089","title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","created":"2023-08-16","cited_by_count":264,"area":null},{"id":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174,"area":null},{"id":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173,"area":null},{"id":"2211.10408","title":"CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow","created":"2022-11-18","cited_by_count":166,"area":null},{"id":"2407.21705","title":"Tora: Trajectory-oriented Diffusion Transformer for Video Generation","created":"2024-07-31","cited_by_count":164,"area":"diffusion"},{"id":"2403.09630","title":"GenAD: Generalized Predictive Model for Autonomous Driving","created":"2024-03-14","cited_by_count":150,"area":"wm"},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142,"area":null},{"id":"2411.00769","title":"GameGen-X: Interactive Open-world Game Video Generation","created":"2024-11-01","cited_by_count":128,"area":"wm"},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124,"area":"deeprl"},{"id":"2503.18938","title":"AdaWorld: Learning Adaptable World Models with Latent Actions","created":"2025-03-24","cited_by_count":114,"area":"wm"},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2403.11447","title":"Motion-aware 3D Gaussian Splatting for Efficient Dynamic Scene Reconstruction","created":"2024-03-18","cited_by_count":100,"area":null},{"id":"2403.00486","title":"Selective-Stereo: Adaptive Frequency Information Selection for Stereo Matching","created":"2024-03-01","cited_by_count":99,"area":null},{"id":"2509.24695","title":"SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer","created":"2025-09-29","cited_by_count":94,"area":"diffusion"},{"id":"2405.20222","title":"MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model","created":"2024-05-30","cited_by_count":89,"area":"diffusion"},{"id":"2503.23377","title":"JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization","created":"2025-03-30","cited_by_count":88,"area":"diffusion"},{"id":"2509.14055","title":"Wan-Animate: Unified Character Animation and Replacement with Holistic Replication","created":"2025-09-17","cited_by_count":80,"area":null},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79,"area":null},{"id":"2312.17681","title":"FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis","created":"2023-12-29","cited_by_count":79,"area":"diffusion"},{"id":"2305.14344","title":"Siamese Masked Autoencoders","created":"2023-05-23","cited_by_count":76,"area":null},{"id":"2408.13770","title":"TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers","created":"2024-08-25","cited_by_count":75,"area":null},{"id":"2312.04565","title":"MuRF: Multi-Baseline Radiance Fields","created":"2023-12-07","cited_by_count":71,"area":null},{"id":"2410.15458","title":"Allegro: Open the Black Box of Commercial-Level Video Generation Model","created":"2024-10-20","cited_by_count":70,"area":null},{"id":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61,"area":null},{"id":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61,"area":null},{"id":"2409.00638","title":"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching","created":"2024-09-01","cited_by_count":59,"area":null},{"id":"2410.06245","title":"HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction","created":"2024-10-08","cited_by_count":57,"area":null},{"id":"2410.10815","title":"Depth Any Video with Scalable Synthetic Data","created":"2024-10-14","cited_by_count":57,"area":"diffusion"},{"id":"2605.15178","title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","created":"2026-05-14","cited_by_count":55,"area":"wm"},{"id":"2501.09466","title":"DEFOM-Stereo: Depth Foundation Model Based Stereo Matching","created":"2025-01-16","cited_by_count":52,"area":null},{"id":"2509.19297","title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","created":"2025-09-23","cited_by_count":48,"area":null},{"id":"2304.11234","title":"Advances in Deep Concealed Scene Understanding","created":"2023-04-21","cited_by_count":47,"area":null},{"id":"2412.04472","title":"Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail","created":"2024-12-05","cited_by_count":47,"area":null},{"id":"2304.12294","title":"Explicit Correspondence Matching for Generalizable Neural Radiance Fields","created":"2023-04-24","cited_by_count":46,"area":null},{"id":"2405.18426","title":"GFlow: Recovering 4D World from Monocular Video","created":"2024-05-28","cited_by_count":46,"area":null},{"id":"2403.08766","title":"MonoOcc: Digging into Monocular Semantic Occupancy Prediction","created":"2024-03-13","cited_by_count":44,"area":null},{"id":"2411.17190","title":"SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting","created":"2024-11-26","cited_by_count":42,"area":null},{"id":"2504.07960","title":"VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning","created":"2025-04-10","cited_by_count":39,"area":"diffusion"},{"id":"2506.09278","title":"UFM: A Simple Path towards Unified Dense Correspondence with Flow","created":"2025-06-10","cited_by_count":36,"area":null},{"id":"2411.10836","title":"AnimateAnything: Consistent and Controllable Animation for Video Generation","created":"2024-11-16","cited_by_count":35,"area":null},{"id":"2412.09349","title":"DisPose: Disentangling Pose Guidance for Controllable Human Image Animation","created":"2024-12-12","cited_by_count":35,"area":null},{"id":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35,"area":null},{"id":"2506.21526","title":"WAFT: Warping-Alone Field Transforms for Optical Flow","created":"2025-06-26","cited_by_count":34,"area":null},{"id":"2403.03447","title":"HDRFlow: Real-Time HDR Video Reconstruction with Large Motions","created":"2024-03-06","cited_by_count":31,"area":null},{"id":"2403.15203","title":"DITTO: Demonstration Imitation by Trajectory Transformation","created":"2024-03-22","cited_by_count":30,"area":null},{"id":"2503.14880","title":"DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework","created":"2025-03-19","cited_by_count":30,"area":null},{"id":"2308.14737","title":"Flexible Techniques for Differentiable Rendering with 3D Gaussians","created":"2023-08-28","cited_by_count":28,"area":null},{"id":"2512.11130","title":"Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching","created":"2025-12-11","cited_by_count":28,"area":"distill"},{"id":"2310.18954","title":"Mask Propagation for Efficient Video Semantic Segmentation","created":"2023-10-29","cited_by_count":26,"area":null},{"id":"2403.19924","title":"SceneTracker: Long-term Scene Flow Estimation Network","created":"2024-03-29","cited_by_count":26,"area":null},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26,"area":null},{"id":"2602.19163","title":"JavisDiT++: Unified Modeling and Optimization for Joint Audio-Video Generation","created":"2026-02-22","cited_by_count":25,"area":null},{"id":"2407.07587","title":"Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction","created":"2024-07-10","cited_by_count":24,"area":null},{"id":"2412.06250","title":"Splatter-360: Generalizable 360$^{\\circ}$ Gaussian Splatting for Wide-baseline Panoramic Images","created":"2024-12-09","cited_by_count":24,"area":null},{"id":"2412.12096","title":"PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting","created":"2024-12-16","cited_by_count":24,"area":null},{"id":"2510.27684","title":"Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals","created":"2025-10-31","cited_by_count":24,"area":"diffusion"},{"id":"2403.05086","title":"UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Sets","created":"2024-03-08","cited_by_count":23,"area":null},{"id":"2404.06261","title":"Playing to Vision Foundation Model's Strengths in Stereo Matching","created":"2024-04-09","cited_by_count":23,"area":null},{"id":"2407.07816","title":"A Survey on Deep Stereo Matching in the Twenties","created":"2024-07-10","cited_by_count":23,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2503.20211","title":"Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors","created":"2025-03-26","cited_by_count":22,"area":null},{"id":"2310.18605","title":"TorchDEQ: A Library for Deep Equilibrium Models","created":"2023-10-28","cited_by_count":21,"area":null},{"id":"2505.21876","title":"EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance","created":"2025-05-28","cited_by_count":21,"area":"diffusion"},{"id":"2312.03018","title":"DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance","created":"2023-12-05","cited_by_count":20,"area":"diffusion"},{"id":"2312.14650","title":"Global Occlusion-Aware Transformer for Robust Stereo Matching","created":"2023-12-22","cited_by_count":19,"area":null},{"id":"2501.08643","title":"MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors","created":"2025-01-15","cited_by_count":19,"area":null},{"id":"2312.09254","title":"Revisiting Depth Completion from a Stereo Matching Perspective for Cross-domain Generalization","created":"2023-12-14","cited_by_count":18,"area":null},{"id":"2410.22817","title":"Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis","created":"2024-10-30","cited_by_count":18,"area":null},{"id":"2503.23282","title":"AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos","created":"2025-03-30","cited_by_count":18,"area":null},{"id":"2308.10079","title":"MeDM: Mediating Image Diffusion Models for Video-to-Video Translation with Temporal Correspondence Guidance","created":"2023-08-19","cited_by_count":17,"area":"diffusion"},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2403.03270","title":"Bi-KVIL: Keypoints-based Visual Imitation Learning of Bimanual Manipulation Tasks","created":"2024-03-05","cited_by_count":16,"area":"offlinerl"},{"id":"2311.02661","title":"CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning","created":"2023-11-05","cited_by_count":15,"area":null},{"id":"2402.00129","title":"CMRNext: Camera to LiDAR Matching in the Wild for Localization and Extrinsic Calibration","created":"2024-01-31","cited_by_count":15,"area":null},{"id":"2403.11120","title":"Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence","created":"2024-03-17","cited_by_count":14,"area":null},{"id":"2410.17772","title":"Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models","created":"2024-10-23","cited_by_count":14,"area":null},{"id":"2411.14847","title":"Dynamics-Aware Gaussian Splatting Streaming Towards Fast On-the-Fly 4D Reconstruction","created":"2024-11-22","cited_by_count":14,"area":null},{"id":"2505.18582","title":"On Denoising Walking Videos for Gait Recognition","created":"2025-05-24","cited_by_count":14,"area":null},{"id":"2506.09565","title":"SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2601.15275","title":"RayRoPE: Projective Ray Positional Encoding for Multi-view Attention","created":"2026-01-21","cited_by_count":14,"area":null},{"id":"2405.17872","title":"HFGS: 4D Gaussian Splatting with Emphasis on Spatial and Temporal High-Frequency Components for Endoscopic Scene Reconstruction","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2408.16478","title":"MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation","created":"2024-08-29","cited_by_count":13,"area":null},{"id":"2310.00632","title":"Win-Win: Training High-Resolution Vision Transformers from Two Windows","created":"2023-10-01","cited_by_count":12,"area":null},{"id":"2405.14873","title":"Federated Online Adaptation for Deep Stereo","created":"2024-05-23","cited_by_count":12,"area":null},{"id":"2408.13005","title":"EasyControl: Transfer ControlNet to Video Diffusion for Controllable Generation and Interpolation","created":"2024-08-23","cited_by_count":12,"area":"diffusion"},{"id":"2412.01316","title":"Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation","created":"2024-12-02","cited_by_count":12,"area":"diffusion"},{"id":"2501.08295","title":"LayerAnimate: Layer-level Control for Animation","created":"2025-01-14","cited_by_count":12,"area":null},{"id":"2502.13078","title":"L4P: Towards Unified Low-Level 4D Vision Perception","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2503.03259","title":"BANet: Bilateral Aggregation Network for Mobile Stereo Matching","created":"2025-03-05","cited_by_count":12,"area":null},{"id":"2507.05963","title":"Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generation","created":"2025-07-08","cited_by_count":12,"area":"diffusion"},{"id":"2402.19270","title":"Learning Intra-view and Cross-view Geometric Knowledge for Stereo Matching","created":"2024-02-29","cited_by_count":11,"area":null},{"id":"2409.05688","title":"LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow","created":"2024-09-09","cited_by_count":11,"area":null},{"id":"2502.03207","title":"MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2502.12752","title":"High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion","created":"2025-02-18","cited_by_count":11,"area":"diffusion"},{"id":"2409.16288","title":"Self-Supervised Any-Point Tracking by Contrastive Random Walks","created":"2024-09-24","cited_by_count":10,"area":null}],"next_cursor":"100"}